INDEX

Explanations

reported speech or citations in the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 SafeMath

-0.60

ientôt

-0.57

hoeddwyd

-0.55

featureID

-0.54

loài

-0.53

iré

-0.53

 cumbre

-0.53

 quæ

-0.51

inerja

-0.51

FromArgb

-0.50

POSITIVE LOGITS

 насеље

0.55

Ligações

0.52

唆

0.50

úrese

0.50

 >=",

0.50

 rispond

0.48

 admits

0.48

 says

0.48

 thinks

0.48

 каже

0.47

Activations Density 0.223%

reported speech or citations in the text

No Comments

No Known Activations